Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    without warranties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.81
     Becken
    -0.75
     Vesu
    -0.75
     febri
    -0.73
    ダイソー
    -0.73
     brachy
    -0.68
    openhagen
    -0.68
    ferien
    -0.66
    Цели
    -0.66
     MTC
    -0.66
    POSITIVE LOGITS
     Cir
    0.73
    Induction
    0.73
     sepeda
    0.69
    toff
    0.68
     ڈ
    0.67
    continental
    0.65
     Singleton
    0.65
    setFile
    0.65
    CppMethod
    0.64
     mainan
    0.63
    Act Density 0.078%

    No Known Activations